Yixiong Hao

Hi! I’m Yixiong, a cs undergrad at Georgia Tech 🐝

I’m not a huge fan of Linkedin or resumes, so here we are — thanks for dropping by :D

I’m very interested the problem called AI alignment because I think it’s super important to figure out how to reliably control exceedingly advanced AI systems (we’re trying to build systems vastly smarter than us as fast as we can, what could go wrong?). Aside from that, I love experiencing new things and learning about different fields and problems (’grokking’ planes of legibility). Maybe one day, if AI safety becomes somewhat solved, I’ll leverage my expertise to build cool things!

Ex-varsity table tennis and golf player, always down to go hit some balls at the range!

This website is always a work in progress 😉

what I look like (apparently)

What I’m up to

UChicago XLab Research Fellowship - Summer 2025, working on a new model organism!
BS in computer science at Georgia Tech 🤓
Advised by Dr Animesh Garg and Dr Kartik Goyal for research in AI safety and robotics
Co-director @ Georgia Tech AI Safety Initiative

Select Research

Patterns and mechanisms of contrastive activation engineering

Y. Hao, A. Panda, S. Shabalin, SAR. Ali

ICLR 2025 Workshops on Bidirectional Human AI Alignment, Human-AI Co-evolution, and Building Trust in LLM Applicationssubst

Paper | Tweet
Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning

S. Shabalin, D. Kharlapenko, A. Panda, SAR. Ali, Y. Hao, A. Conmy

CVPR 2025 Workshops on Mechanistic Interpretability for Vision and Responsible Generative AI

Paper

<aside> 🔭 Always down to connect & chat! → yap (https://cal.com/yixiong) → opportunities and collabs (lmk if there’s anything I can offer!) → build together!

</aside>

Linkedin

Github

Substack